no code implementations • 13 Feb 2024 • Thomas Pöllabauer, Julius Kühn, Jiayi Li, Arjan Kuijper
Estimating the 3D shape of an object using a single image is a difficult problem.
no code implementations • 8 Feb 2024 • Thomas Pöllabauer, Jan Emrich, Volker Knauthe, Arjan Kuijper
Estimating the 6D pose of objects accurately, quickly, and robustly remains a difficult task.
no code implementations • 8 Feb 2024 • Thomas Pöllabauer, Julius Kühn
In medieval times, stuccoworkers used a red color, called sinopia, to first create a sketch of the to-be-made statue on the wall.
no code implementations • 7 Feb 2024 • Thomas Pöllabauer, Fabian Rücker, Andreas Franek, Felix Gorschlüter
Current state-of-the-art 6d pose estimation is too compute intensive to be deployed on edge devices, such as Microsoft HoloLens (2) or Apple iPad, both used for an increasing number of augmented reality applications.
1 code implementation • 15 Sep 2023 • Pavel Rojtberg, Thomas Pöllabauer
Our work introduces the YCB-Ev dataset, which contains synchronized RGB-D frames and event data that enables evaluating 6DoF object pose estimation algorithms using these modalities.
no code implementations • 28 Apr 2020 • Pavel Rojtberg, Thomas Pöllabauer, Arjan Kuijper
Given the dependency of current CNN architectures on a large training set, the possibility of using synthetic data is alluring as it allows generating a virtually infinite amount of labeled training data.